Embeddings, the foundation of retrieval.

using LMKit.Model;
using LMKit.Embeddings;

var model    = LM.LoadFromModelID("embeddinggemma-300m");
var embedder = new Embedder(model);

float[] vec = embedder.GetEmbeddings("Machine learning is fascinating.");
Console.WriteLine($"dimensions: {vec.Length} (matches embedder.EmbeddingSize = {embedder.EmbeddingSize})");

var texts = new[]
{
    "The cat sat on the mat.",
    "A feline rested on the rug.",
    "Stock market closed higher.",
};

// One call, three vectors. GPU batches them efficiently.
float[][] vecs = embedder.GetEmbeddings(texts);

// 0 and 1 are semantically close; 2 is far away.
float simCatRug   = VectorOperations.CosineSimilarity(vecs[0], vecs[1]);
float simCatStock = VectorOperations.CosineSimilarity(vecs[0], vecs[2]);

Console.WriteLine($"cat ~ rug:   {simCatRug:F3}");
Console.WriteLine($"cat ~ stock: {simCatStock:F3}");

using LMKit.Graphics;

// One aligned pair of embedders.
var textEmb  = new Embedder(LM.LoadFromModelID("nomic-embed-text"));
var imageEmb = new Embedder(LM.LoadFromModelID("nomic-embed-vision"));

// Index images.
var store = new FileSystemVectorStore("./image-index");
foreach (var path in Directory.EnumerateFiles("./photos", "*.jpg"))
{
    float[] vec = imageEmb.GetEmbeddings(ImageBuffer.LoadAsRGB(path));
    await store.UpsertAsync(path, vec, new() { ["file"] = path });
}

// Query with TEXT. Retrieves IMAGE results.
float[] query = textEmb.GetEmbeddings("sunset over the ocean");
var hits     = await store.SearchAsync(query, topK: 5);